Byzantine-Tolerant Methods for Distributed Variational Inequalities
Abstract
Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine robustness is relatively well-understood. However, other problem formulations, such as min-max problems or, more generally, variational inequalities, arise in many modern machine learning and, in particular, distributed learning tasks. These problems significantly differ from the standard minimization ones and, therefore, require separate consideration. Nevertheless, only one work (Adibi et al., 2022) addresses this important question in the context of Byzantine robustness. Our work makes a further step in this direction by providing several (provably) Byzantine-robust methods for distributed variational inequality, thoroughly studying their theoretical convergence, removing the limitations of the previous work, and providing numerical comparisons supporting the theoretical findings.
Cite
@article{arxiv.2311.04611,
title = {Byzantine-Tolerant Methods for Distributed Variational Inequalities},
author = {Nazarii Tupitsa and Abdulla Jasem Almansoori and Yanlin Wu and Martin Takáč and Karthik Nandakumar and Samuel Horváth and Eduard Gorbunov},
journal= {arXiv preprint arXiv:2311.04611},
year = {2023}
}
Comments
NeurIPS 2023; 69 pages, 12 figures